Spatial AI Research Scientist: Grounded 3D Perception

Boston Dynamics; Waltham (MA); On-site; USD 177,000 - 225,000; Full time

Job summary

Boston Dynamics is seeking a Spatial AI Research Scientist on the Atlas VLA Research team to advance perception and geometric reasoning for grounded 3D world understanding. You will design real-time SLAM and state estimation on Atlas, and create offline 3D reconstruction pipelines from teleop and robot logs to support large VLM/VLA models.

Collaborate with perception, robotics, ML and system software experts, test on state-of-the-art hardware, and contribute high-quality C++ and Python code.

Qualifications

• PhD in Robotics, CV, ML, CS or related fields (or equivalent research experience).
• Experience building and deploying SLAM, visual odometry, or 3D reconstruction systems for robots or autonomous vehicles.
• Strong background in real-time SLAM, 3D reconstruction, probabilistic state estimation, and spatial representations.
• Strong coding skills in C++ and Python.

Responsibilities

• Design and implement real-time SLAM and perception-based state estimation for a mobile humanoid or specialized data collection devices operating in unstructured, dynamic environments.
• Build offline 3D reconstruction pipelines (multi-view geometry, SfM/MVS, neural reconstruction, depth/pose fusion) that generate geometric scene structure to inform and supervise large VLM/VLA training.
• Pioneer research integrating large VLA and VLM models with 3D spatial perception to enable semantic, language-grounded scene reasoning.
• Bridge classical geometric methods and learned approaches by knowing when to use optimization-based estimation versus learned representations, and how to combine them.
• Write high-quality, maintainable C++ and Python code that fits into a large production codebase.

Skills

C++

Python

SLAM

3D reconstruction

State estimation

Education

PhD in Robotics/Computer Vision/Machine Learning/CS

Tools

PyTorch

JAX

Job description

Boston Dynamics is seeking a Spatial AI Research Scientist on the Atlas VLA Research team to advance perception and geometric reasoning for grounded 3D world understanding. You will design real-time SLAM and state estimation on Atlas, and create offline 3D reconstruction pipelines from teleop and robot logs to support large VLM/VLA models.

Collaborate with perception, robotics, ML and system software experts, test on state-of-the-art hardware, and contribute high-quality C++ and Python code.